Training in progress, step 348, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cf77b4f1ea716a72c126f9f52ff71d162d7064e459728574ac51ac8863ce784
+oid sha256:7da7958fb3316598cd7bd31f14962a4b9f95cac05c29e0e6fb364dd2eb01f50b
 size 1329145928

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d4cdd23b21c04acae9cd565d08c279f300ff00d504f453e44013debf830e0c9
+oid sha256:98fd910ed301d669c3dfc10e6103c6d4a82dee980f2ba7401e4a834f14c2b5f9
 size 841979032

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a7e55b1d5bb15e7a21053569831fe746e36b83ade98888145c8c664203412af
+oid sha256:1683e4c2451132a87e57889d6dcd25b40ca1af97d0d6c414788ddde9fa5bd447
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8f85d6d8690a59509a6114c21bc6a09f49525d54d07da8e164b75d78e5e653b
+oid sha256:24f9209ec94f86ca8913e01c292863444e950b743a761710e89589aaf1adbcb1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 5.301859378814697,
   "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 2.591792656587473,
+  "epoch": 3.0064794816414686,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 348,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,34 @@
       "eval_samples_per_second": 5.949,
       "eval_steps_per_second": 1.495,
       "step": 300
+    },
+    {
+      "epoch": 2.6781857451403885,
+      "grad_norm": 12.293045997619629,
+      "learning_rate": 6.1728263459614796e-06,
+      "loss": 20.8827,
+      "step": 310
+    },
+    {
+      "epoch": 2.7645788336933044,
+      "grad_norm": 18.166112899780273,
+      "learning_rate": 3.367439399426087e-06,
+      "loss": 21.0383,
+      "step": 320
+    },
+    {
+      "epoch": 2.85097192224622,
+      "grad_norm": 17.80660629272461,
+      "learning_rate": 1.396265834701982e-06,
+      "loss": 21.3134,
+      "step": 330
+    },
+    {
+      "epoch": 2.937365010799136,
+      "grad_norm": 16.692588806152344,
+      "learning_rate": 2.7632247671177667e-07,
+      "loss": 20.1229,
+      "step": 340
     }
   ],
   "logging_steps": 10,
@@ -296,12 +324,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.0933430207800934e+18,
+  "total_flos": 1.2504081766652314e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null